https://github.com/zju3dv/manhattan_sdf
공식 코드Neural 3D Scene Reconstruction with the Manhattan-world Assumption
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Creating 3D scene either using conventional SFM pipelines or latest deep learning approaches.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Neural 3D Scene Reconstruction with the Manhattan-world Assumption
CoReNet: Coherent 3D scene reconstruction from a single RGB image
Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single View
Neural RGB->D Sensing: Depth and Uncertainty from a Video Camera
A Pose-only Solution to Visual Reconstruction and Navigation
TransformerFusion: Monocular RGB Scene Reconstruction using Transformers
SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fields
3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior
3D Sketch-aware Semantic Scene Completion via Semi-supervised Structure Prior
Compact 3D Scene Representation via Self-Organizing Gaussian Grids
NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video
CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians
Mirror-3DGS: Incorporating Mirror Reflections into 3D Gaussian Splatting
HOC-Search: Efficient CAD Model and Pose Retrieval from RGB-D Scans
HOC-Search: Efficient CAD Model and Pose Retrieval from RGB-D Scans
HOC-Search: Efficient CAD Model and Pose Retrieval from RGB-D Scans
HuSc3D: Human Sculpture dataset for 3D object reconstruction
NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video
SpikeGS: Reconstruct 3D scene via fast-moving bio-inspired sensors
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.